scholarly journals Monaural Speech Separation Based on Computational Auditory Scene Analysis and Objective Quality Assessment of Speech

2006 ◽  
Author(s):  
Peng Li ◽  
Yong Guan ◽  
Bo Xu ◽  
Wenju Liu
Keyword(s):  
Quality Assessment ◽  
Auditory Scene Analysis ◽  
Scene Analysis ◽  
Speech Separation ◽  
Computational Auditory Scene Analysis ◽  
Objective Quality ◽  
Objective Quality Assessment ◽  
Auditory Scene

An Unsupervised Approach to Close-Talk Speech Enhancement

2014 ◽  
Vol 614 ◽  
pp. 363-366
Author(s):  
Yi Jiang ◽  
Yuan Yuan Zu ◽  
Ying Ze Wang
Keyword(s):  
Speech Enhancement ◽  
Energy Difference ◽  
Auditory Scene Analysis ◽  
Scene Analysis ◽  
Computational Auditory Scene Analysis ◽  
Time Frequency ◽  
Auditory Scene ◽  
Unsupervised Approach ◽  
Frame Work ◽  
Noise Experiment

A K-means based unsupervised approach to close-talk speech enhancement is proposed in this paper. With the frame work of computational auditory scene analysis (CASA), the dual-microphone energy difference (DMED) is used as the cue to classify the noise domain time-frequency (T-F) units and target speech domain units. A ratio mask is used to separate the target speech and noise. Experiment results show the robust performance of the proposed algorithm than the Wiener filtering algorithm.

Sign in / Sign up

Export Citation Format

Share Document